# https://oragent.org/robots.txt
# Allow general crawling. AI/LLM crawlers are explicitly allowed below so the
# site is opt-in to LLM indexing — required for GEO (generative engine
# optimization). Default-deny crawlers (e.g. some LLMs) read the absence of an
# explicit allow as disallow.

User-agent: *
Allow: /

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google (AI Overviews / Gemini training opt-in)
User-agent: Google-Extended
Allow: /

# Common Crawl (feeds many open-source LLMs)
User-agent: CCBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# Bytespider (Doubao / ByteDance)
User-agent: Bytespider
Allow: /

# Meta / Llama
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

Sitemap: https://oragent.org/sitemap-index.xml
